Mobility service providers and others can use cloud platforms to meet customer demand. Due to changing demand or changing technology numerous issues arise. For example, server utilization within the cloud platform can become less efficient over time. As another example, virtual machines and virtual network functions processed by the cloud platform typically need to be extensively tested and certified, which can be expensive. Moreover, intra-platform communication can play a significant role in the costs to operate a cloud platform. Techniques detailed herein can address many of these issues, e.g., by providing mechanisms for increasing host or server utilization in response to changing demand, introducing a container technique for virtual machines to mitigate testing costs, and modeling bandwidth resources.
Legal claims defining the scope of protection, as filed with the USPTO.
1. A network device, comprising: a processor; and a memory that stores executable instructions that, when executed by the processor, facilitate performance of operations, comprising: receiving a request to provision a virtual machine configured to execute a virtual network function according to a network functions virtualization protocol, wherein provisioning the virtual machine allocates defined amounts of resources from among available resources of a group of server devices of a cloud platform; determining state data regarding the group of server devices, wherein the state data comprises location data that identifies members of the group of server devices that are executing existing virtual machines, and resource availability data that indicates the available resources; determining, based on the state data, rearrangement data indicative of a rearrangement solution that transfers execution of an existing virtual machine of the existing virtual machines from a first server device of the group to a second server device of the group, wherein the rearrangement solution is determined to have a lowest cost among potential rearrangement solutions; and in response to the determining the rearrangement data: instructing the second server device to instantiate the existing virtual machine, and instructing the first server device to terminate execution of the existing virtual machine and instantiate the virtual machine.
2. The network device of claim 1 , wherein a resource of the defined amounts of the resources is selected from a resource group comprising a central processing unit resource that executes the virtual network function, a random access memory resource that stores instructions of the virtual network function, a memory storage resource that persistently stores first virtual machine data, an ephemeral storage resource that temporarily stores second virtual machine data, a network interface connection resource that indicates a first number of Ethernet network interface connections that are to be supported by the virtual machine, and a sessions resource that indicates a second number of sessions to be supported by the virtual network function.
3. The network device of claim 1 , further comprising determining the defined amounts of the resources based on a type of the virtual machine.
4. The network device of claim 1 , wherein the determining the rearrangement data is in response to a determination that the resource availability data indicates no individual member of the group of server devices has sufficient available server resources to allocate the defined amounts of the resources and instantiate the virtual machine.
5. The network device of claim 1 , wherein the rearrangement solution is determined to result in the first server device having sufficient available server resources to allocate the defined amounts of the resources and instantiate the virtual machine on the first server device.
6. The network device of claim 1 , wherein the rearrangement solution satisfies an availability constraint that requests the existing virtual machine be accessible to a specified geographical zone or a topological zone of the cloud platform.
7. The network device of claim 1 , wherein the existing virtual machine is a first existing virtual machine, and wherein the rearrangement solution satisfies an affinity constraint that requests the first existing virtual machine have an affinity with a second existing virtual machine.
8. The network device of claim 7 , wherein the affinity is a member of an affinity group comprising: a first affinity indicative of the first existing virtual machine and the second existing virtual machine being executed on a common server device of the group of server devices; a first anti-affinity indicative of the first existing virtual machine and the second existing virtual machine being executed on different server devices of the group of server devices; a second affinity indicative of the first existing virtual machine and the second existing virtual machine being executed on the different server devices, wherein the different server devices share a common chassis communication backplane; and a second anti-affinity indicative of the first existing virtual machine and the second existing virtual machine being executed on the different server devices, wherein the different server devices do not share the common chassis communication backplane.
9. The network device of claim 1 , wherein the lowest cost is determined based on a determination of a resource cost to effectuate the rearrangement solution, comprising a first resource cost to determine the rearrangement solution and a second resource cost to transfer execution of the existing virtual machine.
10. The network device of claim 9 , wherein the resource cost comprises one of a group of resource costs comprising a processing cost, a memory cost, a bandwidth cost, an energy cost, a labor cost, and an unavailability cost.
11. The network device of claim 1 , wherein the operations further comprise, in response to the instructing the second server device to instantiate the existing virtual machine, updating the location data.
12. The network device of claim 1 , wherein the rearrangement data comprises an order for virtual machine instantiations and virtual machine terminations that are determined in connection with the rearrangement solution.
13. A machine-readable storage medium, comprising executable instructions that, when executed by a processor of a device, facilitate performance of operations, comprising: receiving a request to instantiate, on a cloud platform comprising a group of server devices, a virtual machine configured to execute a virtual network function according to a network functions virtualization protocol, wherein instantiating the virtual machine allocates defined amounts of resources from among available resources of the group of server devices; determining state data regarding the group of server devices, wherein the state data comprises location data that identifies server devices of the group that are executing existing virtual machines, and resource availability data that indicates the available resources; based on the state data, determining rearrangement data indicative of a rearrangement solution that transfers execution of an existing virtual machine of the existing virtual machines from a first server device of the group to a second server device of the group, wherein the rearrangement solution is determined to have a lowest cost among potential rearrangement solutions; instructing, according to the rearrangement solution, the second server device to instantiate the existing virtual machine; and instructing, according to the rearrangement solution, the first server device to terminate execution of the existing virtual machine and instantiate the virtual machine.
14. The machine-readable storage medium of claim 13 , wherein the operations further comprise determining the defined amounts of the resources based on a type of the virtual machine.
15. The machine-readable storage medium of claim 13 , wherein the determining the rearrangement data is in response to a determination that the resource availability data indicates no member of the group of server devices has threshold available server resources to allocate the defined amounts of the resources.
16. The machine-readable storage medium of claim 15 , wherein the rearrangement solution is determined to result in the first server device having threshold available server resources to allocate the defined amounts of the resources and instantiate the virtual machine on the first server device.
17. A method, comprising: receiving, by a device comprising a processor, a request to instantiate, via a cloud platform comprising a group of server devices, a virtual machine configured to execute a virtual network function according to a network functions virtualization protocol, wherein instantiating the virtual machine allocates defined amounts of resources from among available resources of the group of server devices; determining, by the processor, state data regarding the group of server devices, wherein the state data comprises location data that identifies server devices of the group that are executing existing virtual machines, and resource availability data that indicates the available resources; based on the state data, determining, by the processor, rearrangement data indicative of a rearrangement solution that transfers execution of an existing virtual machine of the existing virtual machines from a first server device of the group to a second server device of the group, wherein the rearrangement solution is determined to satisfy a cost function relative to other potential rearrangement solutions; and based on the rearrangement solution, facilitating, by the device, transferring the execution of the existing virtual machine from the first server device to the second server device, and facilitating, by the device, instantiating the virtual machine on the first server device.
18. The method of claim 17 , wherein potential rearrangement solutions comprise the rearrangement solution and the other potential rearrangement solutions, and the method further comprising determining, by the device, the potential rearrangement solutions and a respective rearrangement cost of the potential rearrangement solutions.
19. The method of claim 17 , wherein the determining the rearrangement data comprises determining the rearrangement solution subject to a first affinity constraint of the existing virtual machine or subject to a second affinity constraint of the virtual machine.
20. The method of claim 17 , wherein the determining the rearrangement data comprises determining an order of virtual machine instantiations request by the rearrangement solution and virtual machine terminations requested by the rearrangement solution.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
July 27, 2018
April 14, 2020
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.